< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4091 in Layer 19

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 4.0620. Min Range: -4.0620

Max Act: 4.0620. Min Act: -0.1700

Data Index: 3467281 (The Pile)

Max Activating Token Index: 265

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.0620. Min Range: -4.0620

Max Act: 4.0620. Min Act: -0.1700

Data Index: 1294040 (The Pile)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.0620. Min Range: -4.0620

Max Act: 4.0620. Min Act: -0.1700

Data Index: 5774076 (The Pile)

Max Activating Token Index: 454

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.0620. Min Range: -4.0620

Max Act: 4.0620. Min Act: -0.1700

Data Index: 1155791 (The Pile)

Max Activating Token Index: 855

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.0620. Min Range: -4.0620

Max Act: 4.0620. Min Act: -0.1700

Data Index: 2932053 (The Pile)

Max Activating Token Index: 633

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.9995. Min Act: -0.1700

Data Index: 7575947 (The Pile)

Max Activating Token Index: 191

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.9995. Min Act: -0.1700

Data Index: 10223795 (The Pile)

Max Activating Token Index: 568

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.9370. Min Act: -0.1700

Data Index: 1218859 (The Pile)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.9213. Min Act: -0.1700

Data Index: 9438661 (The Pile)

Max Activating Token Index: 380

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8900. Min Act: -0.1700

Data Index: 6117720 (The Pile)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8744. Min Act: -0.1700

Data Index: 4677347 (The Pile)

Max Activating Token Index: 146

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8744. Min Act: -0.1700

Data Index: 5029637 (The Pile)

Max Activating Token Index: 522

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8744. Min Act: -0.1700

Data Index: 506329 (The Pile)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8588. Min Act: -0.1700

Data Index: 2915652 (The Pile)

Max Activating Token Index: 123

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8588. Min Act: -0.1700

Data Index: 4412919 (The Pile)

Max Activating Token Index: 75

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8588. Min Act: -0.1700

Data Index: 7205594 (The Pile)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8275. Min Act: -0.1700

Data Index: 9934467 (The Pile)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8275. Min Act: -0.1700

Data Index: 9532851 (The Pile)

Max Activating Token Index: 693

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8275. Min Act: -0.1700

Data Index: 8581136 (The Pile)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.0620. Min Range: -4.0620

Max Act: 3.8119. Min Act: -0.1700

Data Index: 1203807 (The Pile)

Max Activating Token Index: 383

Click toggle to see full text

Truncated

Full Text #19